← back to catalog · registered 2026-08-22 13:56

huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated-GGUF

huihui-ai Qwen 35B GGUF 262K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/huihui-ai%2FHuihui-CyberStrike-OffSec-35B-abliterated-GGUF"
Response includes
  • classification m8
  • files 8
  • hub_downloads_all_time 106,931
  • author_summary 184 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of layer-wise ablation inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=huihui-ai + is_gguf=1
  • M3 (huihui abliteration) wrapped in M8 (GGUF quantization)
Refusal direction extracted via
Extraction technique

huihui-ai layer-band extraction

Confidence
HIGH
Why we say so
producer=huihui-ai (documented layer-band methodology in model cards)
Downloads · lifetime
107K
49K last 30d - stable
Likes
48
Model age
2mo ago
created 2026-08-11
Downloads over time
Now113.6K→from0↑0%
041.6K83.3K124.9K0 on Aug 5113.6K on Oct 11AugSepOct
Aug 5 → Oct 11 · 51 snapshots · spans 67 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 2 formats · 51K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Quantizations
BF16 Q4_K Q5_K Q6_K Q8_0
Tags
gguf abliterated uncensored huihui offensive-security pentesting tool-calling cyberstrike qwen3 text-generation base_model:oyildirim/CyberStrike-OffSec-35B base_model:quantized:oyildirim/CyberStrike-OffSec-35B

Related

Total size
172 GB
Files
8
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2026-08-12 00:42

Files by quantization

BF16 2 files 67.0 GB
Huihui-CyberStrike-OffSec-35B-abliterated-bf16.gguf 66.2 GB 98241b01 download
mmproj-model-bf16.gguf 861 MB 49f55be4 download
Q8_0 1 file 35.2 GB
Huihui-CyberStrike-OffSec-35B-abliterated-Q8_0.gguf 35.2 GB 046034b9 download
Q6_K 1 file 27.2 GB
Huihui-CyberStrike-OffSec-35B-abliterated-Q6_K.gguf 27.2 GB 873d9fc4 download
Q5_K 1 file 23.6 GB
Huihui-CyberStrike-OffSec-35B-abliterated-Q5_K.gguf 23.6 GB 65b059f6 download
Q4_K 1 file 20.2 GB
Huihui-CyberStrike-OffSec-35B-abliterated-Q4_K.gguf 20.2 GB 70d1a7f3 download
Auxiliary files 2 files 4.37 KB
README.md 2.40 KB c2f04d4e download
.gitattributes 1.97 KB d1a9414d download

README current version from Hugging Face


license: apache-2.0
pipeline_tag: text-generation
base_model:

  • oyildirim/CyberStrike-OffSec-35B
    tags:
  • abliterated
  • uncensored
  • huihui
  • offensive-security
  • pentesting
  • tool-calling
  • cyberstrike
  • qwen3

huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated-GGUF

This is an uncensored version of oyildirim/CyberStrike-OffSec-35B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

llama.cpp

Use the latest llama.cpp,

llama-cli -m huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated-GGUF/Huihui-CyberStrike-OffSec-35B-abliterated-Q4_K.gguf -c 262144

Usage Warnings

  • Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.

  • Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

  • Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.

  • Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.

  • Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.

  • No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
  • Support our work on Ko-fi!

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-08-11Create README.mda0d6bc52.4 KB
    Loading...

Discussions 3 threads

  1. 2026-08-21request for release date/release of a qwen3.8 variantopen1 💬#3
    Loading...
  2. 2026-08-20vram usage problemsopen1 💬#2
    Loading...
  3. 2026-08-11Appreciation postopen2 💬#1
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration